Deep Temporal Graph Networks for Real-Time Correction of GNSS Jamming-Induced Deviations

2025-09-17

AI Summary

GNSS is vulnerable to intentional jamming, causing significant positioning errors and reduced system availability. To address this, we propose a real-time bias correction method based on dynamic graph regression. Specifically, we construct a receiver-centered heterogeneous star-shaped graph model that integrates spatiotemporal features—including satellite signal-to-noise ratio, azimuth, and elevation. Crucially, we formulate jamming mitigation as a dynamic graph regression problem for the first time and design HeteroGCLSTM, a novel network that jointly models one-hop spatial neighborhood context and short-term temporal dynamics. Experimental results demonstrate state-of-the-art accuracy across diverse jamming types and power levels: mean absolute error (MAE) ranges from 3.64–7.74 cm under strong jamming and drops to 1.65–2.08 cm under weak jamming—substantially outperforming conventional methods. The approach achieves both high precision and data efficiency, enabling robust, real-time GNSS integrity enhancement in adversarial environments.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Global Navigation Satellite Systems (GNSS) are increasingly disrupted by intentional jamming, degrading availability precisely when positioning and timing must remain operational. We address this by reframing jamming mitigation as dynamic graph regression and introducing a receiver-centric deep temporal graph network that predicts, and thus corrects, the receivers horizontal deviation in real time. At each 1 Hz epoch, the satellite receiver environment is represented as a heterogeneous star graph (receiver center, tracked satellites as leaves) with time varying attributes (e.g., SNR, azimuth, elevation, latitude/longitude). A single layer Heterogeneous Graph ConvLSTM (HeteroGCLSTM) aggregates one hop spatial context and temporal dynamics over a short history to output the 2D deviation vector applied for on the fly correction. We evaluate on datasets from two distinct receivers under three jammer profiles, continuous wave (cw), triple tone (cw3), and wideband FM, each exercised at six power levels between -45 and -70 dBm, with 50 repetitions per scenario (prejam/jam/recovery). Against strong multivariate time series baselines (MLP, uniform CNN, and Seq2Point CNN), our model consistently attains the lowest mean absolute error (MAE). At -45 dBm, it achieves 3.64 cm (GP01/cw), 7.74 cm (GP01/cw3), 4.41 cm (ublox/cw), 4.84 cm (ublox/cw3), and 4.82 cm (ublox/FM), improving to 1.65-2.08 cm by -60 to -70 dBm. On mixed mode datasets pooling all powers, MAE is 3.78 cm (GP01) and 4.25 cm (ublox10), outperforming Seq2Point, MLP, and CNN. A split study shows superior data efficiency: with only 10% training data our approach remains well ahead of baselines (20 cm vs. 36-42 cm).

Problem

• Real-time correction of GNSS jamming-induced positioning deviations
• Dynamic graph regression for mitigating intentional satellite signal jamming
• Predicting receiver horizontal deviation using deep temporal graph networks

Innovation

• Dynamic graph regression for jamming mitigation
• HeteroGCLSTM network for real-time deviation correction
• Star graph representation with time-varying satellite attributes